© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 108390
    Prev
    Next
    INDEX
    Explanations

    creating, controlling, applying

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ferocious
    0.49
     შემდეგ
    0.48
     je
    0.47
    ens
    0.46
    祟
    0.46
     la
    0.45
     fero
    0.44
    ś
    0.43
    uff
    0.42
     peu
    0.42
    POSITIVE LOGITS
    Ethics
    0.54
    Research
    0.54
    Canvas
    0.54
    Preview
    0.51
    Focus
    0.50
    Systems
    0.50
    Scientific
    0.50
    Reset
    0.49
    Working
    0.49
    Blend
    0.48
    Activations Density 0.003%

    No Known Activations